In-house search-grounded model based on Llama 3.3 70B, optimized for speed and cost-efficiency with real-time web research capabilities. Ideal for straightforward factual queries requiring fast, cited responses with lightweight question-and-answer integration.
- In-house model built on Llama 3.3 70B trained specifically for Perplexity's search engine integration
- Optimized for speed and cost-efficiency delivering fast, accurate responses with comprehensive citations
- Real-time web-wide research capabilities providing up-to-date information with source transparency
- Lightweight integration ideal for applications requiring quick factual answers and Q&A features
- Three search modes (High, Medium, Low) allowing optimization for performance and cost balance
Model Information
Supported Formats
Sonar ProEnhanced search model achieving best-in-class factuality with F-score of 0.858 on SimpleQA benchmark. Designed for complex multi-step tasks with double the citations of base Sonar, providing deeper understanding and context retention.
Sonar ReasoningChain-of-thought reasoning model with embedded live search capabilities, specialized for logical reasoning and step-by-step inference. Excels in mathematical, coding, and analytical challenges requiring sustained reasoning over multiple steps.
Sonar Reasoning ProAdvanced reasoning model powered by DeepSeek-R1 1776 integration, delivering superior step-by-step inference and comparison capabilities. Optimized for research synthesis, evaluation tasks, and complex analytical workflows requiring deep reasoning.